Produção de dados de tráfego sintéticos através de algoritmo genético e simulação microscópica
DOI:
https://doi.org/10.14295/transportes.v18i3.447Abstract
Resumo: Neste artigo, propõe-se um método para produzir, por meio de um simulador, uma série de dados de tráfego sintéticos que representem diversas condições operacionais e comportamentais, como os fornecidos por sensores instalados nas vias. O método proposto baseia-se num algoritmo genético (AG), que automaticamente calibra um modelo de simulação microscópico. Entre os cromossomos (soluções) gerados pelo AG na calibração do simulador, são escolhidos os que produzem resultados marginalmente inferiores ao ótimo. As distribuições de valores dos parâmetros que formam os cromossomos deste subconjunto são usadas para gerar, através de uma amostragem de Monte Carlo, parâmetros para as replicações da simulação que são usadas para produzir os dados sintéticos. A viabilidade do método proposto é demonstrada através de um estudo de caso, no qual o simulador usado foi o TWOPAS e os dados de tráfego foram obtidos de sensores instalados no km 98 da SP98, uma rodovia de pista simples no estado de São Paulo.
Abstract: The paper proposes a method for generating, by a simulator, synthetic traffic data which represents a wide range of operational and behavioral conditions, such as those obtained from detectors installed on roads. The proposed method uses a genetic algorithm (GA) to calibrate a traffic simulation model automatically. A subset of chromosomes (solutions) generated by the GA during the calibration of the simulator containing those that produce results marginally inferior to the best solution is used to produce distributions of feasible values for the simulation model parameters. The distributions of simulation model parameters contained in the chromosomes of this subset of solutions are used to produce, by Monte Carlo sampling, parameters for the simulations that generate the synthetic data. The feasibility of the proposed approach is demonstrated by a case study using TWOPAS and data from detectors installed on SP98, a two-lane highway in the state of São Paulo, Brazil.Downloads
Downloads
Published
How to Cite
Issue
Section
License
Authors who submit papers for publication by TRANSPORTES agree to the following terms:
- Authors retain copyright and grant TRANSPORTES the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors may enter into separate, additional contractual arrangements for the non-exclusive distribution of this journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in TRANSPORTES.
- Authors are allowed and encouraged to post their work online (e.g., in institutional repositories or on their website) after publication of the article. Authors are encouraged to use links to TRANSPORTES (e.g., DOIs or direct links) when posting the article online, as TRANSPORTES is freely available to all readers.
- Authors have secured all necessary clearances and written permissions to published the work and grant copyright under the terms of this agreement. Furthermore, the authors assume full responsibility for any copyright infringements related to the article, exonerating ANPET and TRANSPORTES of any responsibility regarding copyright infringement.
- Authors assume full responsibility for the contents of the article submitted for review, including all necessary clearances for divulgation of data and results, exonerating ANPET and TRANSPORTES of any responsibility regarding to this aspect.
